lrjj

Results 11 issues of lrjj

The QR code of the WeChat group has expired, can I update it?

你好,请问你们的验证集是怎么划分的呢,论文没有体现,我想和你们的方法对比一下,可以告知一下验证集的划分设置吗?

Hello, when I run train.py, why does it keep stuck?(about PAN++) Command used: CUDA_VISIBLE_DEVICES=0,1 python train.py config/pan_pp/pan_pp_r18_ic15_joint_train.py ![1635217872(1)](https://user-images.githubusercontent.com/68632486/138803025-6716e448-5b5b-4ec6-85ae-531889708a3f.jpg)

Who can share the APK installation package of the OCR demo generated by TNN, I want to test it.

下面是编译的部分过程,最后的so文件成功生成了,为什么还是报错呢? ^ src/deform_pool_cuda_kernel.cu:342:60: warning: ??T* at::Tensor::data() const [with T = float]?? is deprecated: Tensor.data() is deprecated. Please use Tensor.data_ptr() instead. [-Wdeprecated-declarations] /home/dong/miniconda3/envs/DB2/lib/python3.7/site-packages/torch/include/ATen/core/TensorBody.h:398:1: note: declared here T * data() const {...

![image](https://user-images.githubusercontent.com/68632486/169758908-cb046aaa-70b8-481e-b6c6-db8919132523.png) 请问你们有遇到过这种情况嘛?我的指令是: CUDA_VISIBLE_DEVICES=0 python eval.py experiments/seg_detector/totaltext_resnet18_deform_thre.yaml --resume ./totaltext_resnet18 --polygon --box_thresh 0.7 测试了IC2015,也是这种情况,全都是0,不知道是什么情况,模型使用的是官方模型

Hello,could u please provide a few samples of your training data and the full scripts for training? Thanks

您好,请问您什么时候公布DB++的代码呢?

您好,请问模型是改了嘛,还是预训练模型不是这样加载的呢? ![521524294f1dd86f5658113d7b47db8](https://user-images.githubusercontent.com/68632486/192452618-e2b912ac-b482-4e46-aac2-48b0e31b1144.jpg) ![f1988f04b93f1116d8904581b2b2b83](https://user-images.githubusercontent.com/68632486/192452625-14900842-8c68-4451-a8d3-7642fa1d5c00.jpg)